Cargando…

Densely Connected Neural Networks for Nonlinear Regression

Densely connected convolutional networks (DenseNet) behave well in image processing. However, for regression tasks, convolutional DenseNet may lose essential information from independent input features. To tackle this issue, we propose a novel DenseNet regression model where convolution and pooling...

Descripción completa

Detalles Bibliográficos
Autores principales: Jiang, Chao, Jiang, Canchen, Chen, Dongwei, Hu, Fei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9317522/
https://www.ncbi.nlm.nih.gov/pubmed/35885098
http://dx.doi.org/10.3390/e24070876
_version_ 1784755077827788800
author Jiang, Chao
Jiang, Canchen
Chen, Dongwei
Hu, Fei
author_facet Jiang, Chao
Jiang, Canchen
Chen, Dongwei
Hu, Fei
author_sort Jiang, Chao
collection PubMed
description Densely connected convolutional networks (DenseNet) behave well in image processing. However, for regression tasks, convolutional DenseNet may lose essential information from independent input features. To tackle this issue, we propose a novel DenseNet regression model where convolution and pooling layers are replaced by fully connected layers and the original concatenation shortcuts are maintained to reuse the feature. To investigate the effects of depth and input dimensions of the proposed model, careful validations are performed by extensive numerical simulation. The results give an optimal depth (19) and recommend a limited input dimension (under 200). Furthermore, compared with the baseline models, including support vector regression, decision tree regression, and residual regression, our proposed model with the optimal depth performs best. Ultimately, DenseNet regression is applied to predict relative humidity, and the outcome shows a high correlation with observations, which indicates that our model could advance environmental data science.
format Online
Article
Text
id pubmed-9317522
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-93175222022-07-27 Densely Connected Neural Networks for Nonlinear Regression Jiang, Chao Jiang, Canchen Chen, Dongwei Hu, Fei Entropy (Basel) Article Densely connected convolutional networks (DenseNet) behave well in image processing. However, for regression tasks, convolutional DenseNet may lose essential information from independent input features. To tackle this issue, we propose a novel DenseNet regression model where convolution and pooling layers are replaced by fully connected layers and the original concatenation shortcuts are maintained to reuse the feature. To investigate the effects of depth and input dimensions of the proposed model, careful validations are performed by extensive numerical simulation. The results give an optimal depth (19) and recommend a limited input dimension (under 200). Furthermore, compared with the baseline models, including support vector regression, decision tree regression, and residual regression, our proposed model with the optimal depth performs best. Ultimately, DenseNet regression is applied to predict relative humidity, and the outcome shows a high correlation with observations, which indicates that our model could advance environmental data science. MDPI 2022-06-25 /pmc/articles/PMC9317522/ /pubmed/35885098 http://dx.doi.org/10.3390/e24070876 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Jiang, Chao
Jiang, Canchen
Chen, Dongwei
Hu, Fei
Densely Connected Neural Networks for Nonlinear Regression
title Densely Connected Neural Networks for Nonlinear Regression
title_full Densely Connected Neural Networks for Nonlinear Regression
title_fullStr Densely Connected Neural Networks for Nonlinear Regression
title_full_unstemmed Densely Connected Neural Networks for Nonlinear Regression
title_short Densely Connected Neural Networks for Nonlinear Regression
title_sort densely connected neural networks for nonlinear regression
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9317522/
https://www.ncbi.nlm.nih.gov/pubmed/35885098
http://dx.doi.org/10.3390/e24070876
work_keys_str_mv AT jiangchao denselyconnectedneuralnetworksfornonlinearregression
AT jiangcanchen denselyconnectedneuralnetworksfornonlinearregression
AT chendongwei denselyconnectedneuralnetworksfornonlinearregression
AT hufei denselyconnectedneuralnetworksfornonlinearregression